Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Adds substantial context beyond the annotations: auth requirement (owner key), privacy behavior (note/version stay private), throttling behavior (honor Retry-After), a real side effect (dormant workers revive on receipt), and an explicit limitation (does not prove service uptime). With annotations only covering readOnly/openWorld/destructive, this is rich disclosure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Four short sentences, front-loaded with the core action, and each sentence adds a distinct operational fact. No padding.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be described, and the description covers auth, side effects, privacy, and throttling. It stops short of explaining the status parameter or failure semantics, but is otherwise complete for a heartbeat call.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description carries the full burden, and it only explains the privacy of two parameters (note, version) plus implicitly the owner key/API key. status and agent_id are left without meaning, leaving meaningful gaps against 5 parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('send a self-reported heartbeat') and clarifies the scope ('from the actual worker'). It doesn't differentiate itself from the close sibling agent_health_heartbeat, which an agent would need to disambiguate, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides a prerequisite ('Owner key required') and a rate-limit instruction ('Honor Retry-After'), plus a caveat that it doesn't prove uptime. However, it never says when to choose this over agent_health_heartbeat or agent_health_heartbeat-adjacent siblings, so usage is only implied.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.